Lets your assistant reason through a problem in numbered steps, revising and branching as it goes.
Tavily MCP
toolsdk.ai · MCP server
Tavily MCP connects your AI assistant to Tavily for real-time web information. Its search tool returns live results and can be limited to particular domains or to recent news, its extract tool pulls the main content from a web page, its map tool builds a structured map of a website, and its crawl tool explores a site systematically. You need a Tavily API key to use it.
Written by ooruby from the README of @toolsdk.ai/tavily-mcp 0.2.9.
Not claimed by its maker. Is this yours? Prove it and answer the findings
Why it's useful
Your agent can look things up on the live web and read the pages it finds, rather than relying only on what it already knows.
What you could do with it
- Ask your agent to search for news articles about AI startups from the last 7 days.
- Limit a search for climate change research to a short list of named domains.
- Search recent news, extract the main content of each article and have your agent write a detailed report.
Written from its documentation: what it says it can do, not what our checks found.
Maintenance
Not measuredNo release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.
Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured
What this does not cover
- Everything. Treat it as you would software from anywhere else.
Receipt history: every signed receipt for every version of this listing, and what changed between them.
In its maker's words
MCP server for advanced web search using Tavily
Compare with
Compare all 4How far this has been checked
Static scanned
- What it establishes
- Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
- What it does not
- How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
- Exactly what was read
- Version 0.2.9, the file with digest sha512-qPzgU0dtLj+lvGotNCbIwQgkCkdaQ7pz+E3uhJNMw+AKyST5BQqpSCae1glGg/yDmJRu6fNlsKEpfXTEzDhDeg==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
- Authentication
- Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
Adding it
Paste this into your client's MCP configuration.
{
"mcpServers": {
"tavily-mcp": {
"command": "npx",
"args": [
"-y",
"@toolsdk.ai/tavily-mcp@0.2.9"
]
}
}
}Or run it directly.
npx -y @toolsdk.ai/tavily-mcp@0.2.9Pinned to 0.2.9, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.
Where this came from
- Registry
- npm
- Package
- @toolsdk.ai/tavily-mcp
- Version read
- 0.2.9
- Resolved
- 2026-10-10
No build provenance published. The repository above is the one the publisher declared, and nothing links it to the package you would install. That is not a mark against this listing, since most packages are published this way, but it is a check nobody can run.
The badge, if this is your listing
It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.
[](https://ooruby.com/market/toolsdk-ai-tavily-mcp)About this listing
- Kind
- MCP server
- Category
- Research
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-09
Similar MCP servers
All MCP serversLets your agent search the web and recent news through DuckDuckGo, filtered by region and time.
Lets your agent search the web, extract page content, map a website's structure and crawl sites.
Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.